AINeutralarXiv – CS AI · Mar 34/105
🧠
Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
Researchers propose RapTB, a new training objective for Generative Flow Networks (GFlowNets) that addresses mode collapse issues in fine-tuning large language models. The method includes a submodular replay strategy (SubM) and demonstrates improved performance in molecule generation tasks while maintaining diversity and validity.